Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

Loading page content

© 2026 Leaderboard.cn. Traceable AI model evaluations and rankings.

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

MMMU Pro (no tools)Multimodal

Results for 10 models collected from 5 public sources.

#ModelScore

1

GPT-5.6 SolOpenAI

83.0%

2

81.2%

3

81.2%

4

GPT-5.6 TerraOpenAI

80.7%

5

Gemini 3.1 ProGoogle

80.5%

6

79.5%

7

GPT-5.6 LunaOpenAI

78.4%

8

GPT-5.4 miniOpenAI

76.6%

9

GPT-5 miniOpenAI

67.5%

10

GPT-5.4 nanoOpenAI

66.1%

10 models total